India's Sarvam launches Token Factory hosting Kimi, GLM, DeepSeek open models
itsOmSarraf_ · x · 2026-11-16
India's Sarvam has made its Token Factory generally available, hosting its own models and leading open-weight LLMs — Kimi-K3.1 Pro, GLM-5.3, GLM-5.3 Flash, DeepSeek V4.1-flash 1017, DeepSeek V4 Pro and more — on Sarvam infrastructure in India.
- Access: one OpenAI-compatible API (api.sarvam.ai/v2); same API key, SDK and credits as all other Sarvam APIs — switching from OpenAI takes a two-line change.
- Pricing (₹ per 1M tokens): GLM-5.3 at 126/390, GLM-5.3 Flash 13.5/45, DeepSeek V4.1 Flash 1017 at 14/55 (intro through end of 2026), Sarvam 105B at 10/25, Gemma 4 31B at 35/90.
- Pitch: enterprises get more model choice and an ownable AI stack without lock-ins, with performance and reliability matching leading inference providers.
More from Infra
- A 10-item beginner reading list for LLM distributed training, from Horovod to FSDP — East-Muffin-6472 · 2026-11-17
- 18MB browser-run TTS model tiny-voca makes paid English TTS look silly — thisdudelikesAI · 2026-11-17
- Replicate quietly switches nano banana outputs from JPG downloads to presigned URLs — Kyrannio · 2026-11-17
- Fireworks AI tells investors chips are a commodity, its moat is software that runs models fast — hargup13 · 2026-11-17
- Claude-written CUDA C++ port runs TRELLIS.2 5.3x faster on H200, bit-identical — huggingface · 2026-11-17
- China to make 3M AI ASICs in 2027 vs West's 20M, each ~4x faster per chip — teortaxesTex · 2026-11-17